EP4064711A1 - Procédé et appareil de fourniture d'un flux vidéo basé sur l'apprentissage automatique - Google Patents

Procédé et appareil de fourniture d'un flux vidéo basé sur l'apprentissage automatique Download PDF

Info

Publication number
EP4064711A1
EP4064711A1 EP22162178.2A EP22162178A EP4064711A1 EP 4064711 A1 EP4064711 A1 EP 4064711A1 EP 22162178 A EP22162178 A EP 22162178A EP 4064711 A1 EP4064711 A1 EP 4064711A1
Authority
EP
European Patent Office
Prior art keywords
video stream
event
server
streaming
basis
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP22162178.2A
Other languages
German (de)
English (en)
Inventor
Sang Il Ahn
Yong Je Lee
Hyeon U Park
Beom Jun Shin
Gi Hoon Yeom
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hyperconnect LLC
Original Assignee
Hyperconnect LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hyperconnect LLC filed Critical Hyperconnect LLC
Publication of EP4064711A1 publication Critical patent/EP4064711A1/fr
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/454—Content or additional data filtering, e.g. blocking advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/44—Event detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Definitions

  • the present disclosure relates to a method and an apparatus for providing a video stream based on machine learning.
  • an administrator is needed to monitor whether harmful elements are included in each video during the multi-party video call service or the real-time personal broadcast service and to impose sanctions on users who transmit inappropriate videos.
  • the matter to be achieved by the present example embodiments is to provide a method and an apparatus capable of automatically identifying whether harmful elements are included in a video stream transmitted in real time using at least one model (for example, a learning model trained through machine learning) and restricting transmission of a corresponding video stream.
  • at least one model for example, a learning model trained through machine learning
  • a method of providing a video stream based on machine learning of an electronic device includes: receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream using a learning model trained through machine learning on the basis of at least one frame of the source video stream, and determining whether to restrict streaming of the source video stream from the first device on the basis of the event detection.
  • a method of providing a video stream based on machine learning of an electronic device includes: receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream on the basis of at least one frame of the source video stream, and restricting streaming of the source video stream from the first device in response to the event detection.
  • an electronic device includes a communication module, a database, and a processor.
  • the processor may be set to receive a source video stream which is streamed from a first device to at least one other, confirm whether an event is detected on the source video stream using a learning model trained through machine learning on the basis of at least one frame of the source video stream, and determine whether to restrict streaming of the source video stream from the first device on the basis of the event detection.
  • an electronic device in another embodiment, includes a communication module, a database, and a processor.
  • the processor may be set to receive a source video stream which is streamed from a first device to at least one other, confirm whether an event is detected on the basis of at least one frame of the source video stream, and restrict streaming of the source video stream from the first device in response to the event detection.
  • a computer-readable non-transitory recording medium for recording a program includes executing a method of providing a video stream based on machine learning on an electronic device.
  • the method of providing a video stream based on machine learning may include receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream using a learning model trained through machine learning on the basis of at least one frame of the source video stream, and determining whether to restrict streaming of the source video stream from the first device on the basis of the event detection.
  • a computer-readable non-transitory recording medium for recording a program includes executing a method of providing a video stream on an electronic device.
  • a method of providing a video stream may include receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream on the basis of at least one frame of the source video stream, and restricting streaming of the source video stream from the first device in response to the event detection.
  • A, B, and C may include the following meanings: A alone; B alone; C alone; both A and B together; both A and C together; both B and C together; and all three of A, B, and C together.
  • An “electronic device” referred to below may be implemented as a computer or a portable terminal capable of accessing a server or other electronic device through a network.
  • the computer includes, for example, a desktop, and a laptop, which are equipped with a web browser; and the portable terminal includes, for example, a wireless communication device which ensures portability and mobility, and may include all types of handheld-based wireless communication devices including terminals based on communication, such as international mobile telecommunication (IMT), code division multiple access (CDMA), w-code division multiple access (W-CDMA), long term evolution (LTE), smartphones, and tablet personal computers (PCs).
  • IMT international mobile telecommunication
  • CDMA code division multiple access
  • W-CDMA w-code division multiple access
  • LTE long term evolution
  • smartphones smartphones, and tablet personal computers (PCs).
  • Streaming described herein may correspond to a concept classified into commercial and consumer models as a service provided to produce and transmit a video in real time or to watch such a video.
  • each block of flowchart diagrams and combinations of the flowchart diagrams may be performed by computer program instructions.
  • These computer program instructions may be embodied in a processor of a general purpose computer, a special purpose computer, or other programmable data processing equipment such that the instructions performed by the processor of the computer or other programmable data processing equipment generate parts for performing functions described in flowchart block(s).
  • These computer program instructions may use a computer or other programmable data processing equipment for implementing a function in a specific manner or may be stored in a computer readable memory, and thus the instructions which use the computer or are stored in the computer readable memory can produce a manufacturing article including instruction parts for performing the functions described in the flowchart block(s).
  • the computer program instructions can also be embedded in the computer or other programmable data processing equipment, these instructions can provide operations for performing the functions described in the flowchart block(s), as they are a series of operations that are performed on the computer or other programmable data processing equipment to generate a computer-executed process, thereby operating the computer or other programmable data processing equipment.
  • each block may represent a module, segment, or a portion of a code, which includes one or more executable instructions for executing specified logical function(s). It is also to be noted that, in some alternative embodiments, it is also possible for the functions mentioned in the blocks to occur out of the order. For example, two blocks shown in succession can be substantially performed simultaneously or, in sometimes, the two blocks can be performed in the reverse order according to corresponding functions.
  • FIG. 1A is a diagram illustrating a network environment according to various example embodiments of the present disclosure.
  • a network environment 1 may include at least one electronic device 110, at least one server 120, and a network 50.
  • four electronic devices 110 and two servers 120 are illustrated as an example of the network environment 1, and the network environment 1 according to various example embodiments of the present disclosure is not limited to the number of the electronic devices 110 or the number of the servers 120 and may include various types of network environments to which the following example embodiments may be applied.
  • the electronic device 110 may include a fixed terminal or a mobile terminal implemented as a computer device.
  • the electronic device 110 may include at least one among a smartphone, a mobile phone, a navigation device, a computer, a notebook, a digital broadcast terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, and a wearable device.
  • PDA personal digital assistant
  • PMP portable multimedia player
  • a tablet PC a wearable device.
  • a specific electronic device 110 is shown in the form of a smartphone in FIG. 1A , this may correspond to a variety of physical computer devices capable of actually communicating with another electronic device 110 and/or the server 120 using a wireless or wired communication method through the network 50.
  • At least one of the electronic devices 110 may correspond to a video provider device (for example, a host device or a guest device) which generates a video stream and transmits the video stream to a server (for example, a media server) or another electronic device (for example, a video viewer device) in a streaming transmission method.
  • a video provider device for example, a host device or a guest device
  • another electronic device for example, a video viewer device
  • at least one other of the electronic devices 110 may correspond to a video viewer device which receives a video stream generated by the video provider device and outputs the video stream through a display and/or a speaker.
  • the electronic device 110 may be a device corresponding to a monitoring agent which monitors occurrence of an event regarding whether a harmful element is included in a video stream generated by a specific video provider device.
  • the network 50 may facilitate connections between the electronic device 110 and the server 120; the electronic device 110 and another electronic device 110; or the server 120 and another server 120.
  • the network 50 may provide an access path such that each device may be connected to each other to transmit/receive packet data.
  • the network 50 may be implemented in a communication method using communication networks (for example, a mobile communication network, a wired Internet, a wireless Internet, and a broadcast network) and in various short-range wireless communication methods.
  • the network 50 may include at least one among networks such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet.
  • network 50 may be implemented as at least one network topologies including but not limited to a bus network, a star network, a ring network, a mesh network, a star-bus network, and a tree or hierarchical network.
  • the server 120 may include a plurality of computer systems implemented as a network server or computer software and may configure and provide various pieces of information in the form of a web page.
  • the server 120 may refer to a computer system and computer software which is connected to a sub-device capable of communicating with another network server through a computer network such as the Intranet or the Internet to receive a request for performing a task, perform the task, and provide an execution result.
  • the server 120 may be understood as a broad concept including a series of application programs capable of being operated on a network server and various databases built in the network server.
  • the server 120 may be implemented using network server programs which are variously provided according to an operating system (OS) such as a disk OS (DOS), Windows, Linux, universal network information exchange (UNIX), or a Macintosh (Mac) OS.
  • OS operating system
  • the server 120 may be implemented as a computer device (or a plurality of computer devices) which communicates with another electronic device 110 or another server 120 through the network 50 and transmits and receives various pieces of information such as commands, codes, files, or contents.
  • the server 120 may include a media server which receives a video generated from a specific video provider device (for example, a host device or a guest device) in a streaming method and transmits the received video stream to a plurality of other electronic devices (for example, video viewer devices) in the streaming method.
  • a media server may store the received video stream in a queue and sequentially transmit the received video stream to a plurality of electronic devices in the streaming method.
  • the server 120 may include a machine learning server corresponding to any one among the plurality of electronic devices which receive a video stream from the media server.
  • the machine learning server may include at least one learning model trained through machine learning and confirm whether an event is detected for a video stream using the learning model.
  • the machine learning server may restrict streaming transmission from the video provider device which provides the video stream or transmit information related to the event detection to a device corresponding to the monitoring agent through an application programming interface (API) server, thereby reconfirming whether the event is detected.
  • API application programming interface
  • the API server may provide the information related to the event detection received from the machine learning server to a specific electronic device 110 corresponding to the monitoring agent (administrator), and the monitoring agent may electively restrict streaming transmission by the electronic device correspond to the video provider on the basis of the received information.
  • FIG. 1B is a block diagram illustrating a configuration of an electronic device according to various example embodiments of the present disclosure.
  • the electronic device 110 is a user device using a real-time personal broadcast service (or a multi-party video call service) and may correspond to any one of a video provider device which provides a video or a video viewer device which receives and outputs the video.
  • the electronic device may be a video provider device or a video viewer device according to circumstances.
  • the electronic device 110 is a device corresponding to a monitoring agent which manages occurrence of an event related to video content (for example, a video stream) generated by a specific video provider device and may correspond to a monitoring agent device.
  • the electronic device 110 may include at least one among a processor 111, a memory 113, a communication module 115, an input module 117, and an output module 119.
  • the processor 111 of the electronic device 110 may generate video content using a camera and/or a microphone included in the input module 117. Processor 111 may transmit the generated video content or receive specific information (or a content) from another device using the communication module 115. In addition, the processor 111 may output a specific video content using a display and/or a speaker included in the output module 119 and store or withdraw a series of commands or predetermined data related to an operation of the electronic device 110 through the memory 113.
  • FIG. 1C is a block diagram illustrating a configuration of a server according to various example embodiments of the present disclosure.
  • the server 120 may include at least one among a processor 121, a database 123, and a communication module 125.
  • the processor 121 of the server 120 may transmit a predetermined video content (for example, a video stream) received from a specific device to another device using the communication module 125 or may detect a specific event on the basis of the received video.
  • the processor 121 may maintain or restrict transmission of the video content on the basis of the detection of the event and may provide evaluation information on a specific device (for example, the video provider device), for example, registers as an abusive user.
  • the processor 121 may confirm whether the event is detected for the predetermined video content (for example, the video stream) using at least one model (for example, at least one learning model trained through machine learning) pre-stored in the database 123, and when an event is detected for a specific video content, the processor 121 may transmit the detected information related to the event to another device (for example, the monitoring agent device).
  • the predetermined video content for example, the video stream
  • at least one model for example, at least one learning model trained through machine learning
  • the processor 121 may perform a series of operations for processing various functions implemented in the server 120.
  • the processor 121 may receive learning data (for example, video content information confirmed as corresponding to the event) and train the learning model using the learning data through machine learning.
  • the learning model has been trained using learning data which comprises video frames containing video content information representing an event (at least one specific event) which shall be detected in video frames using the trained learning model.
  • the learning model may be a classification model.
  • the database 123 is a data structure implemented in a predetermined storage space of the server 120 and may have fields or components for processing functions such as storage, search, deletion, editing, or addition of data.
  • the database 123 may be electrically connected to the processor 121 and store commands related to the operations of the processor 121.
  • the database 123 may store various pieces of data used in the server 120 (for example, learning data, commands for machine learning, critical condition information related to a probability value, and information related to a frame sampling condition).
  • FIGS. 2 and 3 are schematic flowcharts illustrating a method of providing a video stream according to various example embodiments of the present disclosure.
  • a video stream may be generated by a first electronic device 110a (for example, a video provider device) first.
  • a video provider corresponding to the first electronic device 110a may correspond to a user who intends to provide a video stream using a real-time personal broadcast service (or a multi-party video call service).
  • the video provider may generate a predetermined video stream (or video contents) using predetermined input modules (for example, a camera and a microphone) included in the first electronic device 110a.
  • Image data and/or audio data may be included in the video stream.
  • the first electronic device 110a may transmit the generated video stream to a media server 120b in a real-time streaming method.
  • the media server 120b may transmit the received video stream to a plurality of other devices (for example, video viewer devices) again.
  • the media server 120b may serve to relay the video stream between the video provider device and the video viewer device.
  • the video stream since the video stream generated by the first electronic device 110a is streamed to other devices, the video stream may be referred to as a source stream.
  • the plurality of other devices receiving the video stream from the media server 120b may each include a third electronic device(s) 110c (for example, the video viewer device) and a machine learning server 120c.
  • a video viewer corresponding to the third electronic device 110c may correspond to a user who is provided with a predetermined video stream using a real-time personal broadcast service (or a multi-party video call service).
  • the video viewer may confirm (view) a video output in real time using output modules (for example, a display and a speaker) provided in the third electronic device 110c.
  • the third electronic device 110c may refer to a plurality of video viewer devices corresponding to a plurality of video viewers viewing the video stream received from the media server 120b.
  • the machine learning server 120c may correspond to a monitoring device prepared to detect a situation (event) in which an inappropriate video is provided to the third electronic device 110c (that is, the video viewer device) within a short time and act on the detected situation (event).
  • the machine learning server 120c may receive a video stream in real time from at least one video provider (for example, the first electronic device 110a such as a host or a guest) which generates the video stream by participating in the real-time personal broadcast service (or the multi-party video call service) and confirm whether an event is detected for the video stream in real time.
  • the first electronic device 110a such as a host or a guest
  • the media server 120b may store (keep) the video stream received from the first electronic device 110a in a queue first and provide the video stream to the plurality of other devices in a streaming method according to a predetermined processing method.
  • the machine learning server 120c may confirm whether an event is detected for the video stream received through the media server 120b.
  • the machine learning server 120c may store at least one learning model trained through machine learning in advance in a database and confirm in real time whether a specified event occurs in the video stream transmitted in real time using the learning model.
  • the learning model trained through the machine learning may include a neural network having two or more layers.
  • the learning model trained through the machine learning may include an input layer, an output layer, and at least one hidden layer.
  • the learning model may include a classification model which is previously trained using training data obtained by classifying at least one piece of video data and/or at least one piece of audio data into a normal element and an abnormal element (for example, a harmful element).
  • the learning model may extract predetermined features from arbitrary video data and/or arbitrary audio data and use the extracted features as input data, thereby confirming whether an abnormal element (for example, a harmful element) is included in the video data and/or the voice data (that is, whether an event is detected).
  • an abnormal element for example, a harmful element
  • the learning model may further provide a probability value related to reliability of the output data.
  • the machine learning server 120c may directly reflect a monitoring result on the video stream in a method of restricting video streaming transmission from the first electronic device 110a on the basis of the output data.
  • the machine learning server 120c may ignore the output data or transmit a reconfirmation request for the event detection to another device (for example, the second electronic device 110b).
  • the threshold value may include a first threshold value and a second threshold value.
  • the machine learning server 120c may request the second electronic device 110b to reconfirm the event detection and restrict streaming on the basis of a response of the second electronic device 110b.
  • the machine learning server 120c may directly restrict the streaming in response to acquisition of the probability value. Reconfirming the event may include a user input of a user of the second electronic device 110b in response to presenting the video frame to the user of the second electronic device 110b.
  • the machine learning server 120c may interrupt a confirmation operation whether an event is included in the video stream from the first electronic device 110a for a specified time (for example, twenty-four hours).
  • the machine learning server 120c may determine a user corresponding to the first electronic device 110a as an abusive user and may omit a confirmation operation on whether an event is detected on the video stream provided from the first electronic device 110a.
  • the machine learning server 120c may restrict streaming transmission of the video stream generated by the user corresponding to the first electronic device 110a for a specified time regardless of identification information on a broadcast through which the video stream is streamed.
  • the machine learning server 120c may transmit information related to the event, which includes a command for restricting transmission of the video stream, to the media server 120b.
  • the media server 120b may interrupt streaming transmission of the video stream corresponding to the event to the third electronic device 110c.
  • the media server 120b may transmit information for notifying that provision of the video stream from the first electronic device 110a is interrupted to the third electronic device 110c.
  • a stream streamed to the third electronic device 110c may be referred to as a target stream, and the target stream may include a video corresponding to at least one source stream.
  • one stream may be generated by merging several source streams, and thus a plurality of users may perform a broadcast through one stream.
  • provision of at least a portion of the video stream may be interrupted in a method of restricting transmission of a portion corresponding to the source stream in which the event is detected of the target stream.
  • the event is detected in some streams of the broadcast including a plurality of source streams, in order to improve user experience, it is possible to more frequently determine whether the event is detected on the source stream included in the target stream and/or to perform more strictly event determination by changing a threshold value setting for event determination.
  • the machine learning server 120c may provide at least one of notification information for indicating that the event is detected from the video stream and notification information for indicating that streaming of the video stream is restricted to the first electronic device 110a which generates the video stream corresponding to the detected event.
  • the media server 120b confirming the event detection of the video stream from the machine learning server 120c may transmit event detection notification information and/or notification information for indicating that streaming of the video stream is restricted to the first electronic device 110a, on behalf of the machine learning server 120c.
  • any one among the machine learning server 120c, the media server 120b, the API server 120a may manage an event detection history of the user by registering the user (for example, the video provider) corresponding to the first electronic device 110a, which generates the video stream corresponding to the detected event, as an abusive user.
  • the method of providing a video stream according to an example embodiment described with reference to FIG. 2 may correspond to a method, when the predetermined event is detected from the specific video stream in the machine learning server 120c, which is applied merely when the probability value related to the event detection provided as a reliability index of the event detection is greater than or equal to a specified threshold value. Meanwhile, when the probability value related to the event detection is smaller than the specified threshold value, a method of providing a video stream according to an example embodiment described below with reference to FIG. 3 may be applied.
  • the method of providing a video stream may provide a video stream according to each operation shown in FIG. 2 , and when the probability value related to the event detection is less than the specified threshold value, the method of providing a video stream may ignore an event detection result (that is, the output data) or provide report suggestion information related to the event detection to the video viewer device (for example, the third electronic device 110c).
  • an event detection result that is, the output data
  • report suggestion information related to the event detection to the video viewer device
  • a method of providing a video stream according to still another example embodiment may provide a video stream according to each operation shown in FIG. 3 at any time, regardless of whether the probability value related to the event detection is smaller than the specified threshold value.
  • a video stream generated by the first electronic device 110a in operation 310 may be transmitted to the media server 120b in operation 320, and the video stream may be transmitted from the media server 120b to a plurality of other devices (for example, the machine learning server 120c and the third electronic device 110c) in operation 330.
  • the machine learning server 120c may confirm whether an event is detected in the received video stream using a learning model trained through machine learning.
  • the above-described operations 310 to 340 may correspond to substantially the same operations as operations 210 to 240 described with reference to FIG. 2 .
  • the machine learning server 120c may then transmit information related to the detected event to the API server 120a in operation 350.
  • the machine learning server 120c when the detection of the event is confirmed in operation 340, the machine learning server 120c according to an example embodiment performs the following operations on the basis of whether the probability value related to the detection of the event is smaller than a specified threshold value. In certain embodiments, merely when the probability value related to the event detection is less than the specified threshold value, in operation 350, the machine learning server 120c may transmit information related to the video stream corresponding to the detected event, that is, event related information, to the API server 120a. In addition, in operation 360, the API server 120a may transmit the event related information to the second electronic device 110b.
  • the second electronic device 110 is an electronic device corresponding to the monitoring agent (for example, an administrator) may receive predetermined information for reconfirming whether the event is detected on a specific video stream, which is primarily confirmed by the machine learning server 120c.
  • the specific video stream may be presented to a user of the second electronic device 110 who, by user input into the second electronic device 110, either reconfirms or negates the event.
  • the second electronic device 110b to which the API server 120a transmits the event related information in operation 360 may refer to one or more external devices.
  • the API server 120a (or the machine learning server 120c) may determine the number of external devices, to which the event related information is to be transmitted, on the basis of a magnitude of the probability value.
  • the API server 120a may transmit the event related information to a single external device (for example, a first external device).
  • the API server 120a may transmit the event related information to two or more external devices (for example, the first external device and a second external device).
  • the first external device and the second external device may correspond to electronic devices corresponding to different monitoring agents, respectively.
  • the API server 120a may reconfirm whether the event is detected through an external device(s) on the basis that the event related probability value is smaller than a set magnitude and may set the number of times of reconfirmation (or re-censorship) to two or more times on the basis of the magnitude of the probability value.
  • the machine learning server 120c may additionally train the learning model on the basis of reconfirmation result information on whether the event is detected, which is received from the second electronic device 110b (for example, at least one of the first external device and the second external device).
  • the information related to the event detection may include at least one among time stamp information corresponding to a point of time when the event occurs in the video stream in relation to the video stream in which the event is detected, frame information corresponding to a portion of the video stream in which the event is identified, user (for example, the video provider) identification (ID) information corresponding to the first electronic device 110a which generates the video stream, and broadcast identification (ID) information related to the video stream (for example, a stream ID or a broadcast ID).
  • both of information on at least one previous frame (for example, second frame information) and information on at least one subsequent frame (for example, third frame information) of the specific frame are transmitted to the second electronic device 110b, and the second electronic device 110b may assist with confirming a context of the specific frame on the basis of the pieces of transmitted information.
  • a plurality of video streams generated from two or more first electronic devices 110a (for example, video provider devices) in one broadcast may be simultaneously provided through partial regions allocated in one screen.
  • a video provider which newly generates a specific broadcast and provides a video stream through the generated broadcast, may correspond to a host, and another video provider, which provides a video stream by participating in the already generated broadcast, may correspond to a guest.
  • an administrator device for example, the API server 120a or the media server 120b
  • broadcast ID information for example, the API server 120a or the media server 120b
  • the administrator device may assign stream ID information (stream ID) corresponding to the video stream with respect to the video stream provided from the device corresponding to the host device.
  • stream ID information for example, the stream ID information (stream ID) with respect to a video stream provided from a device corresponding to the guest.
  • the first electronic device 110a may correspond to at least one of the host device or the guest device.
  • the machine learning server 120c may confirm at least one of stream ID information (stream ID) corresponding to the specific video stream and broadcast ID information (broadcast ID) of a broadcast to which the specific video stream is provided.
  • the pieces of information may be received from the media server 120b at a point of time when streaming transmission of the video stream is started from the media server 120b in operation 330.
  • the machine learning server 120c may provide the API server 120a with the stream ID information (stream ID) of the video stream corresponding to the identified event, and in operation 360, the API server 120a may provide the second electronic device 110b with the stream ID information (stream ID) and the broadcast ID information (broadcast ID).
  • the API server 120a may confirm the broadcast ID information (broadcast ID) corresponding to the stream ID information (stream ID) on the basis of the received stream ID information (stream ID) and may transmit the confirmed broadcast ID information (broadcast ID) together with the stream ID information (stream ID) to the second electronic device 110b.
  • the machine learning server 120c may directly transmit the event related information to the second electronic device 110b.
  • the media server 120b may provide the information related to the event detection to the API server 120a (or the second electronic device 110b).
  • the second electronic device 110b may output content data of at least a portion of a video stream corresponding to the event confirmed by the machine learning server 120c on the basis of the received event related information and receive an input from the user (for example, the monitoring agent (administrator)) to reconfirm whether the event is detected in the video stream.
  • the user for example, the monitoring agent (administrator)
  • the second electronic device 110b may transmit the event related information including a command to restrict streaming transmission of the video stream to the media server 120b in operation 380, and in operation 385, the media server 120b may interrupt transmission of the video stream.
  • the second electronic device 110b in response to the reconfirmation of the detection of the event in the video stream, may also provide notification information on the event detection and the transmission restriction of the video stream to the first electronic device 110a.
  • the second electronic device 110b may manage an event detection history of the user in a method of registering the user (for example, the video provider) corresponding to the first electronic device 110a as an abusive user.
  • the second electronic device 110b when the detection of the event in the video stream is reconfirmed, may provide data related to the confirmation result to the machine learning server 120c as additional learning data, and the machine learning server 120c may perform machine training on the learning model on the basis of the additional learning data.
  • FIG. 4 is a flowchart illustrating a method of providing a video stream based on machine learning of an apparatus (for example, the machine learning server 120c of FIG. 2 ) according to an example embodiment of the present disclosure.
  • a device may receive a video stream which is generated from a first device (for example, the first electronic device 110a of FIG. 2 ) to be transmitted to a plurality of other devices (for example, the third electronic device 110c of FIG. 2 ).
  • a first device for example, the first electronic device 110a of FIG. 2
  • a plurality of other devices for example, the third electronic device 110c of FIG. 2 .
  • the first device may correspond to a video provider device which generates and transmits a video stream
  • the plurality of other devices may at least include a device corresponding to a video viewer device which receives the video stream in a streaming method.
  • the device may directly receive the video stream, which is generated by the first device, from the first device or indirectly receive the video stream through an intermediate device (for example, the media server 120b of FIG. 2 ) which receives the video stream and then transmits the video stream to the device and the plurality of other devices.
  • an intermediate device for example, the media server 120b of FIG. 2
  • the device may determine whether a predetermined event is detected in the video stream received in real time in operation 410 using at least one learning model trained through machine learning.
  • the event may be about whether a video (for example, image data and/or audio data) corresponding to at least one among an abusive gesture, an insult gesture, a legislative gesture, a sexual content, nudity, genitalia, sexual activity, unsanitary contents, excrement, defecation, antisocial contents, anti-human contents, other illegal activity, criminal activity, violent activity, abusive activity, self-harm, weapons, drugs, antisocial symbols, hateful contents, threatening content, phobia-inducing contents, and blood is included.
  • the device may pre-train the learning model using learning data obtained by classifying the event into a plurality of event types and may be implemented in a method of confirming whether a specific video corresponds to at least one among the plurality of divided event types.
  • the learning model may be trained using a deep learning algorithm.
  • the learning model may be trained using an algorithm including at least one among a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a region-based convolutional neural network (R-CNN), a deep belief network (DBN), a deep quantum (Q)-network.
  • DNN deep neural network
  • CNN convolutional neural network
  • RNN recurrent neural network
  • R-CNN region-based convolutional neural network
  • DBN deep belief network
  • Q deep quantum
  • the device may provide the video stream or restrict streaming of the video stream using various types of logic models.
  • the device may be implemented through a model in which at least some of the various operations described as being performed using a machine learning model in the present specification is consisting of a predetermined decision tree.
  • the device in order to efficiently process the event detection, may sample at least some of frames from the video stream received from the first device according to a specified condition and may confirm whether an event is detected on the basis of the at least sampled data (for example, the at least some frames).
  • FIG. 5 is a diagram for describing a method of sampling a video stream according to an example embodiment of the present disclosure.
  • the device may sample some frames 424 among frames 422 included in a received video stream according to a specified condition.
  • the device may acquire the sampled frames 424 by extracting at least some of the frames 422 included in the video stream at every unit of a specified time or by extracting at least some of the frames 422 at every unit of specified number of frames.
  • the device may adjust a computational load of the device or selectively adjust accuracy of event detection by controlling the sampling condition.
  • the device may control the sampling condition on the basis of user ID information corresponding to the first device (for example, the video provider device) which provides the video stream.
  • the first device for example, the video provider device
  • the device may be set to sample a frame at a relatively short time period or at a period of a small number of frames with respect to the video stream provided from the first device corresponding to the video provider.
  • frames of a video stream provided from the first device corresponding to the video provider may be set to be sampled at a relatively long time period or a large number of frames.
  • the device may control the computational load in a method of setting the sampling condition to sample the frames at every short time period or a small number of frames.
  • the device may restrict provision of the video stream from the first device which is the video provider device corresponding to the video stream in which the event is detected.
  • the device when it is determined that the event is detected, may directly restrict streaming transmission of the video stream from the first device.
  • the device may block the user corresponding to a source stream in which the event is detected from performing a broadcast for a set time, restrict all streaming of other source streams previously generated by the user (regardless of the broadcast ID information of each streaming), or interrupt an event detection operation on the source stream generated by the user for a specified period of time.
  • a device may transmit information related to the video stream corresponding to the event to a second device, for example, a monitoring agent device (for example, the second electronic device 110b of FIG. 2 ), instead of the device restricting streaming transmission directly from the first device in order to additionally reconfirm whether the event is detected.
  • the device may directly transmit the information related to the video stream corresponding to the event to the monitoring agent device or indirectly transmit the information (the information related to the video stream) to the monitoring agent device through an API server (for example, the API server 120a of FIG. 2 ).
  • the second device may include one or more external devices, and the number of the one or more external devices may be determined on the basis of a magnitude of the probability value related to the event detection.
  • the probability value for example, a probability value related to reliability of the event detection
  • a first threshold value for example, 0.8
  • a second threshold value for example 0.95
  • the device may transmit the information to one external device (for example, a first monitoring agent device) and receive result information related to the event detection, thereby reconfirming whether the event is detected.
  • the device may transmit the information to two different external devices (for example, the first monitoring agent device and a second monitoring agent device) and receive the result information related to the event detection from each of the two different external devices, thereby reconfirming whether the event is detected.
  • the device may transmit the information to three or more external devices to reconfirm whether the event is detected three or more times or may ignore data related to the event detection corresponding to the probability value.
  • the device may transmit at least one among time stamp information corresponding to the event, frame information corresponding to the event, user ID information corresponding to the first device, and broadcast ID information related to the video stream (for example, stream ID information (stream ID) and/or broadcast ID information (broadcast ID)) to the second device.
  • broadcast ID information for example, stream ID information (stream ID) and/or broadcast ID information (broadcast ID)
  • the device may transmit a frame in which the event is detected and frame(s) immediately before the frame (and frame(s) immediately after the frame).
  • the second device may receive user (administrator) input information on whether an event is detected in the video stream and confirm whether an actual event corresponds to an event detection case in which the probability value is less than a specified threshold value through the user (administrator) input information.
  • the device such as the machine learning server 102c, may additionally train the learning model on the basis of reconfirmation result information related to the event detection received from the second device.
  • the device in designating a threshold value to be compared with the probability value, when the existing event detection history of a user (video provider) corresponding to the first device is present on the basis of the user ID information corresponding to the first device, the device may identify whether an event occurs in the video stream on the basis of a based on stricter standards by designating the threshold as a relatively large value.
  • at least one model for example, a learning model trained through machine learning
  • the electronic device or server may include a processor, a memory for storing and executing program data, a permanent storage such as a disk drive, a communication port for communicating with an external device, and user interface devices such as touch panels, keys, and buttons.
  • Methods implemented as software modules or algorithms may be computer-readable codes or program instructions executable on the processor and be stored on a computer-readable recording medium.
  • the computer-readable recording medium includes a magnetic storage medium (for example, a read-only memory (ROM), a random-access memory (RAM), a floppy disk, and a hard disk) and an optically readable medium (for example, a compact disc (CD)-ROM and a digital versatile disc (DVD)).
  • the computer-readable recording medium may also be distributed in a computer system connected via a network so that a computer-readable program or code can be stored and executed in a distributed manner.
  • the computer-readable recording medium may be readable by a computer, stored in a memory, and executed by a processor.
  • the example embodiments may be represented by functional block components and various processing operations. These functional blocks may be implemented in various numbers of hardware and/or software configurations which perform specific functions.
  • the example embodiments may employ integrated circuit components, such as a memory, processing, a logic, a look-up table, capable of executing various functions under the control of one or more microprocessors or other control devices.
  • the components may be implemented as software programming or software components
  • the example embodiments may include various algorithms implemented in a combination of data structures, processes, routines, or other programming components and may be implemented in a programming or scripting language such as C, C++, Java, or an assembler.
  • the functional aspects may be implemented with algorithms running on one or more processors.
  • example embodiments may employ the related art for an electronic environment setting, signal processing, and/or data processing.
  • Terms such as “mechanism,” “element,” “part,” and “component” may be used broadly and are not limited to mechanical and physical components. These terms may include the meaning of a series of routines of software in association with a processor or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
EP22162178.2A 2021-03-22 2022-03-15 Procédé et appareil de fourniture d'un flux vidéo basé sur l'apprentissage automatique Pending EP4064711A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020210036704A KR102576636B1 (ko) 2021-03-22 2021-03-22 기계 학습 기반 영상 스트림 제공 방법 및 장치

Publications (1)

Publication Number Publication Date
EP4064711A1 true EP4064711A1 (fr) 2022-09-28

Family

ID=80781033

Family Applications (1)

Application Number Title Priority Date Filing Date
EP22162178.2A Pending EP4064711A1 (fr) 2021-03-22 2022-03-15 Procédé et appareil de fourniture d'un flux vidéo basé sur l'apprentissage automatique

Country Status (4)

Country Link
US (1) US20220303621A1 (fr)
EP (1) EP4064711A1 (fr)
JP (1) JP2022146903A (fr)
KR (1) KR102576636B1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11810343B2 (en) * 2021-05-11 2023-11-07 Asio Advanced Control Solutions Ltd Artificial intuition based visual data extraction for distributed systems
CN116363686B (zh) * 2023-06-02 2023-08-11 深圳大学 一种在线社交网络视频平台来源检测方法及其相关设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018221824A1 (fr) * 2017-05-27 2018-12-06 Hyperconnect, Inc. Dispositif de communication vidéo et procédé de communication vidéo
US20190253744A1 (en) * 2018-02-13 2019-08-15 Ernest Huang Systems and methods for content management of live or streaming broadcasts and video publishing systems
US20190373322A1 (en) * 2018-05-29 2019-12-05 Sony Interactive Entertainment LLC Interactive Video Content Delivery

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8019702B1 (en) * 2007-12-07 2011-09-13 Google Inc. Supervised learning with multi-scale time intervals using a statistical classification model to classify unlabeled events
KR101062672B1 (ko) * 2010-01-05 2011-09-06 (주)필링크 유해 동영상 검출장치 및 그 방법
KR20150128151A (ko) * 2014-05-08 2015-11-18 삼성전자주식회사 비디오 스트리밍 방법 및 이를 지원하는 전자 장치
US10528712B2 (en) * 2016-12-28 2020-01-07 Motorola Solutions, Inc. Detection of unauthorized user assistance of an electronic device based on the detection of spoken words
KR101932844B1 (ko) * 2017-04-17 2018-12-27 주식회사 하이퍼커넥트 영상 통화 장치, 영상 통화 방법 및 영상 통화 중개 방법
US20190122258A1 (en) * 2017-10-23 2019-04-25 Adbank Inc. Detection system for identifying abuse and fraud using artificial intelligence across a peer-to-peer distributed content or payment networks
KR102104397B1 (ko) * 2017-12-05 2020-04-24 이원 유해물 관리 방법, 이를 실행하는 컴퓨팅 장치 및 컴퓨터 프로그램
US11430238B1 (en) * 2019-06-26 2022-08-30 Apple Inc. Generating a contextual information vector for improved scene understanding
KR102169073B1 (ko) * 2019-09-30 2020-10-22 광운대학교 산학협력단 동영상 유해성 분석 결과 기반 실시간 스트리밍 차단 시스템 및 방법
WO2021150033A1 (fr) * 2020-01-23 2021-07-29 Samsung Electronics Co., Ltd. Dispositif électronique et procédé de commande de dispositif électronique
US20220124407A1 (en) * 2020-10-21 2022-04-21 Plantronics, Inc. Content rated data stream filtering
KR102225100B1 (ko) * 2020-10-29 2021-03-09 주식회사 지란지교데이터 인공지능을 이용한 dna 기반 음란 영상 차단 방법 및 장치

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018221824A1 (fr) * 2017-05-27 2018-12-06 Hyperconnect, Inc. Dispositif de communication vidéo et procédé de communication vidéo
US20190253744A1 (en) * 2018-02-13 2019-08-15 Ernest Huang Systems and methods for content management of live or streaming broadcasts and video publishing systems
US20190373322A1 (en) * 2018-05-29 2019-12-05 Sony Interactive Entertainment LLC Interactive Video Content Delivery

Also Published As

Publication number Publication date
US20220303621A1 (en) 2022-09-22
KR102576636B1 (ko) 2023-09-11
JP2022146903A (ja) 2022-10-05
KR20220131701A (ko) 2022-09-29

Similar Documents

Publication Publication Date Title
JP6983887B2 (ja) モバイルアプリケーションのリアルタイム遠隔制御のためのシステムおよび方法
US11455830B2 (en) Face recognition method and apparatus, electronic device, and storage medium
EP4064711A1 (fr) Procédé et appareil de fourniture d'un flux vidéo basé sur l'apprentissage automatique
US10182095B2 (en) Method and system for video call using two-way communication of visual or auditory effect
US20170289619A1 (en) Method for positioning video, terminal apparatus and cloud server
US11830496B2 (en) Generating and providing inclusivity data insights for evaluating participants in a communication
US8997134B2 (en) Controlling presentation flow based on content element feedback
US11044206B2 (en) Live video anomaly detection
US10528674B2 (en) Cognitive agent for capturing referential information during conversation muting
US11228542B2 (en) Systems and methods for communication channel recommendations using machine learning
US11792251B2 (en) Media stream network action decisions
EP3469495A1 (fr) Procédés, systèmes et supports pour présenter une interface utilisateur personnalisée pour une activité d'utilisateur prédite
US11665010B2 (en) Intelligent meeting recording using artificial intelligence algorithms
US20190141068A1 (en) Online service abuser detection
CN112083853A (zh) 账号举报方法、审核方法、装置、电子设备和存储介质
CN109783337B (zh) 模型服务方法、系统、装置和计算机可读存储介质
US11675492B2 (en) Determining user engagement in content based on scrolling events
CN117056008A (zh) 一种弹窗拦截方法及装置、设备及介质
US11272254B1 (en) System, method, and computer program for using user attention data to make content recommendations
US20220383089A1 (en) Intelligent meeting hosting using artificial intelligence algorithms
CN114697763B (zh) 一种视频处理方法、装置、电子设备及介质
CN113052632B (zh) 一种广告流量数据的识别方法、装置、设备及存储介质
US11902038B2 (en) Securing data presented during videoconferencing
EP4304183A1 (fr) Appareil de détection d'utilisateur d'interruption de service et procédé associé
US20230412851A1 (en) Incident category selection optimization

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

RAP3 Party data changed (applicant data changed or rights of an application transferred)

Owner name: HYPERCONNECT LLC

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20230327

RBV Designated contracting states (corrected)

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20240523